# US 2012/0251009 A1 · Image processing apparatus, image processing method, and computer-readable recording device

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2012/0251009 A1
- Document ID: US20120251009A1
- Status: Published application
- Kind: A1
- Application number: 13/404,470
- Filed: 2012-02-24
- Published: 2012-10-04
- Earliest claimed: 2011-03-31
- Assignees: Olympus Corporation
- Inventors: Yamato KANDA; Makoto KITAMURA; Takashi KONO; Masashi HIROTA
- Web page: https://patentgrep.com/patent/US20120251009A1

## CPC

- G06T 7/0012: {Biomedical image inspection}
- G06T 2207/20036: Morphological image processing
- G06T 2207/30021: Catheter; Guide wire
- G06T 2207/30096: Tumor; Lesion
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

An image processing apparatus includes an approximate-surface calculator that calculates multiple approximate surfaces that each approximate the pixel value of a pixel included in an examination-target region of an image; an approximate-surface selector that selects at least one approximate surface from the approximate surfaces on the basis of the relation between the pixel value of the pixel in the examination-target region and the approximate surfaces; an approximate-region setting unit that sets an approximate region that is approximated by at least the selected one approximate surface; and an abnormal-region detector that detects an abnormal region on the basis of the pixel value of a pixel in the approximate region and the value corresponding to the coordinates of that pixel on at least one approximate surface.

## Claims

### Claim 1

An image processing apparatus comprising:
an approximate-surface calculator that calculates multiple approximate surfaces that approximate a pixel value of a pixel included in an examination-target region of an image;
an approximate-surface selector that selects at least one approximate surface from the approximate surfaces on the basis of the relation between a pixel value of a pixel in the examination-target region and the approximate surfaces;
an approximate-region setting unit that sets an approximate region where the pixel value of the pixel is approximated by at least the selected one of the approximate surfaces; and
an abnormal-region detector that detects an abnormal region on the basis of a pixel value of a pixel in the approximate region and a value at the coordinates of the pixel on at least the selected one of the approximate surfaces.

### Claim 2 (depends on 1)

The image processing apparatus according to claim 1, wherein the approximate-surface calculator includes
a pixel extracting unit that extracts multiple pixels from the examination-target region, the pixels being used for calculating each of the approximate surfaces, and
an approximate-function calculator that calculates an approximate function that includes the coordinates of an extracted pixel as variables and approximates a pixel value at the coordinates.

### Claim 3 (depends on 1)

The image processing apparatus according to claim 1, wherein the approximate-surface calculator further includes a number-of-calculations setting unit that sets the number of times calculation of an approximate surface is performed on the basis of information about the examination-target region.

### Claim 4 (depends on 3)

The image processing apparatus according to claim 3, wherein the number-of-calculations setting unit includes a size calculator that calculates the size of the examination-target region, and sets the number of times calculation of an approximate surface is performed by using the size as information about the examination-target region.

### Claim 5 (depends on 3)

The image processing apparatus according to claim 3, wherein the number-of-calculations setting unit further includes a number-of-edges calculator that calculates the number of edges included in the examination-target region, and sets the number of times calculation of an approximate surface is performed by using the number of edges as information about the examination-target region.

### Claim 6 (depends on 2)

The image processing apparatus according to claim 2, wherein the pixel extracting unit includes an extraction-area setting unit that sets, in the examination-target region, an area from which multiple pixels are extracted, the pixels being used for calculating each of the approximate surfaces, and extracts the pixels from the area.

### Claim 7 (depends on 6)

The image processing apparatus according to claim 6, wherein the extraction-area setting unit includes a local-region setting unit that sets a local region as the area, and
the pixel extracting unit extracts the pixels from the area.

### Claim 8 (depends on 6)

The image processing apparatus according to claim 6, wherein the extraction-area setting unit includes a region connecting unit that connects adjacent pixels in the examination-target region so as to obtain one connected region, and
the pixel extracting unit extracts the pixels from the same connected region.

### Claim 9 (depends on 1)

The image processing apparatus according to claim 1, wherein
the approximate-surface selector includes
an approximate-surface close-region detector that detects, for each approximate surface, an approximate-surface close region where a pixel value of a pixel in the examination-target region is close to a value at the coordinates of the pixel on at least the selected one of the approximate surfaces, and
an approximate evaluation-value calculator that calculates an evaluation value that indicates the degree of approximation of an approximate surface in the approximate-surface close region, and
the approximate-surface selector selects at least one approximate surface from the approximate surfaces on the basis of the evaluation value.

### Claim 10 (depends on 9)

The image processing apparatus according to claim 9, wherein the approximate-surface close-region detector includes a difference-value calculator that calculates, for each approximate surface, the difference value between a pixel value of a pixel in the examination-target region and a value at the coordinates of the pixel on at least the selected one of the approximate surfaces, and compares the difference value with a predetermined threshold so as to detect the approximate-surface close region.

### Claim 11 (depends on 9)

The image processing apparatus according to claim 9, wherein the approximate evaluation-value calculator includes a size calculator that calculates the size of the approximate-surface close region as the evaluation value, and
the approximate-surface selector selects an approximate surface for which the approximate-surface close region has the largest size.

### Claim 12 (depends on 9)

The image processing apparatus according to claim 9, wherein the approximate evaluation-value calculator includes a variance-value calculator that calculates, as the evaluation value, variance of the difference value between a pixel value of a pixel in the approximate-surface close region and a value at the coordinates of the pixel on at least the selected one of the approximate surfaces, and
the approximate-surface selector selects an approximate surface with which the variance is the least.

### Claim 13 (depends on 9)

The image processing apparatus according to claim 9, wherein the approximate evaluation-value calculator includes a region connecting unit that connects adjacent pixels in the approximate-surface close region so as to obtain one connected region, and calculates the evaluation value with respect to the same connected region.

### Claim 14 (depends on 1)

The image processing apparatus according to claim 1, wherein
the approximate-region setting unit includes
a candidate-region detector that detects a candidate region of the approximate region; and
a candidate-region deforming unit that deforms the candidate region, and
the approximate-region setting unit sets the candidate region deformed by the candidate-region deforming unit as the approximate region.

### Claim 15 (depends on 14)

The image processing apparatus according to claim 14, wherein the candidate-region detector includes a difference-value calculator that calculates, for each approximate surface, the difference value between a pixel value of a pixel in the examination-target region and a value at the coordinates of the pixel on at least the selected one of the approximate surfaces, and compares the difference value with a predetermined value so as to detect a candidate region.

### Claim 16 (depends on 15)

The image processing apparatus according to claim 15, wherein
the candidate-region detector further includes
a region connecting unit that connects adjacent pixels in the candidate region so as to obtain one connected region; and
a size calculator that calculates the size of the connected region, and
the candidate-region detector selects the connected region that has the largest size as a final candidate region.

### Claim 17 (depends on 14)

The image processing apparatus according to claim 14, wherein the candidate-region deforming unit includes a morphological operation unit that performs a morphological operation on the candidate region, and
the approximate-region setting unit sets the candidate region deformed due to the morphological operation as the approximate region.

### Claim 18 (depends on 14)

The image processing apparatus according to claim 14, wherein the candidate-region deforming unit includes an inclusion-region combining unit that combines the candidate region with an inclusion region included in the candidate region, and
the approximate-region setting unit sets the candidate region deformed by combining the inclusion region as the approximate region.

### Claim 19 (depends on 18)

The image processing apparatus according to claim 18, wherein
the inclusion-region combining unit includes
an inclusion-region detector that detects an inclusion region included in the candidate region, and
an inclusion-region information calculator that calculates information about the inclusion region, and
the inclusion-region combining unit combines the inclusion region with the candidate region if the information about the inclusion region satisfies a predetermined condition.

### Claim 20 (depends on 1)

The image processing apparatus according to claim 1, further comprising an approximate-surface re-calculator that recalculates an approximate surface that approximates a pixel value of a pixel in the approximate region on the basis of pixel values of multiple pixels in the approximate region.

### Claim 21 (depends on 20)

The image processing apparatus according to claim 20, wherein the approximate-surface re-calculator includes
a weight setting unit that sets a weight to a pixel in the approximate region, and
an approximate-function calculator that calculates an approximate function that uses the weight, includes the coordinates of a pixel in the approximate region as variables, and approximates a pixel value at the coordinates.

### Claim 22 (depends on 21)

The image processing apparatus according to claim 21, wherein the weight setting unit includes a difference-value calculator that calculates the difference value between a pixel value of a pixel in the approximate region and the approximate value at the coordinates of the pixel on the calculated approximate surface, and sets a weight to each pixel in accordance with the difference value.

### Claim 23 (depends on 21)

The image processing apparatus according to claim 21, wherein the weight setting unit includes a contour-pixel detector that detects a contour pixel in the approximate region, and sets a higher weight to the contour pixel than to pixels other than the contour pixel.

### Claim 24 (depends on 1)

The image processing apparatus according to claim 1, wherein the abnormal-region detector includes a difference-value calculator that calculates the difference value between a pixel value of a pixel in the approximate region and a value at the coordinates of the pixel on at least the selected one of the approximate surfaces, and compares the difference value with a predetermined threshold so as to detect an abnormal region.

### Claim 25 (depends on 1)

The image processing apparatus according to claim 1, further comprising a target-region resetting unit that sets, as a new examination-target region, a region other than the approximate region set by the approximate-region setting unit and that performs control so as to repeat the processes performed by the approximate-surface calculator, the approximate-surface selector, and the approximate-region setting unit.

### Claim 26

An image processing method comprising:
calculating multiple approximate surfaces that approximate a pixel value of a pixel included in an examination-target region of an image;
selecting at least one approximate surface from the approximate surfaces on the basis of the relation between a pixel value of a pixel in the examination-target region and the approximate surfaces;
setting an approximate region where a pixel value of the pixel is approximated by at least the selected one of the approximate surfaces; and
detecting an abnormal region on the basis of a pixel value of a pixel in the approximate region and a value at the coordinates of the pixel on at least the selected one of the approximate surfaces.

### Claim 27

A computer-readable recording device with an executable program stored thereon, wherein the program instructs a processor to execute:
calculating multiple approximate surfaces that approximate a pixel value of a pixel included in an examination-target region of an image;
selecting at least one approximate surface from the approximate surfaces on the basis of the relation between a pixel value of a pixel in the examination-target region and the approximate surfaces;
setting an approximate region where a pixel value of the pixel is approximated by at least the selected one of the approximate surfaces; and
detecting an abnormal region on the basis of a pixel value of a pixel in the approximate region and a value at the coordinates of the pixel on at least the selected one of the approximate surfaces.
